Autonomous Robots- Visual Perception in Underground Terrains Using Statistical Region Merging

Authors: Omowunmi E. Isafiade, Isaac O. Osunmakinde, Antoine B. Bagula

Abstract:

Robots- visual perception is a field that is gaining increasing attention from researchers. This is partly due to emerging trends in the commercial availability of 3D scanning systems or devices that produce a high information accuracy level for a variety of applications. In the history of mining, the mortality rate of mine workers has been alarming and robots exhibit a great deal of potentials to tackle safety issues in mines. However, an effective vision system is crucial to safe autonomous navigation in underground terrains. This work investigates robots- perception in underground terrains (mines and tunnels) using statistical region merging (SRM) model. SRM reconstructs the main structural components of an imagery by a simple but effective statistical analysis. An investigation is conducted on different regions of the mine, such as the shaft, stope and gallery, using publicly available mine frames, with a stream of locally captured mine images. An investigation is also conducted on a stream of underground tunnel image frames, using the XBOX Kinect 3D sensors. The Kinect sensors produce streams of red, green and blue (RGB) and depth images of 640 x 480 resolution at 30 frames per second. Integrating the depth information to drivability gives a strong cue to the analysis, which detects 3D results augmenting drivable and non-drivable regions in 2D. The results of the 2D and 3D experiment with different terrains, mines and tunnels, together with the qualitative and quantitative evaluation, reveal that a good drivable region can be detected in dynamic underground terrains.

Keywords: Drivable Region Detection, Kinect Sensor, Robots' Perception, SRM, Underground Terrains.

Digital Object Identifier (DOI): doi.org/10.5281/zenodo.1329460

References:

[1] S. Chen and Y. Li and N. Ming, Active Vision in Robotic Systems: A Survey of Recent Developments, The International Journal of Robotics Research, AID: 0278364911410755, Vol. 30, No. 11 ,pp. 1343 1377, September, 2011.
[2] A. Damarupurshad, African (Mining-Related) Government Departments, Mineral/Mining-Related Organisations and Mining Companies with Interests in Africa, Journal of Minerals and Energy (Republic of South Africa), Vol. D13, No. 1 ,pp. 1-58, June, 2004.
[3] PricewaterhouseCoopers. SA Mine: Review of Trends in the South African Mining Industry, SA Mine, Vol. 6 No. 1, pp. 1-48, November 2011.
[4] C.J.H. Hartnady, South Africa-s Gold Production and Reserves, South African Journal of Science, Vol. 105, No. 1 ,pp. 328-330, September, 2009.
[5] M. A. Hermanus, Occupational Health and Safety in Mining- Status, New Developments and Concerns, Journal of the Southern African Institute of Mining and Metallurgy, Vol. 107, No. 1 ,pp. 531-538, May, 2007.
[6] J. J. Green and K. Hlophe and J. Dickens and R. Teleka and M. Price, Mining Robotics Sensors, International Journal of Engineering and Advanced Technology (IJEAT), Vol. 1, No. 4 ,pp. 8-15, April, 2012.
[7] J. Benjamin and Y. Papelis and R. Pillat and G. Stein and D. Harper,A Practical Approach to Robotic Design for the DARPA Urban Challenge, International Journal of Field Robotics, Vol. 25, No. 8 ,pp. 528-566, July, 2008.
[8] T. Joaquin and N. Patricio, A New Approach to Visual-Based Sensory System for Navigation into Orange Groves, Journal of MDPI Open Access Sensors, Vol. 11, pp. 4086-4103, April 2011.
[9] H. Derek and A. Alexei and H. Martial. Recovering Surface Layout from an Image, International Journal of Computer Vision, Vol. 75, pp.151-172, 2007.
[10] S. Scheding and G. Dissanayake and E. Nebot and H. Durrant-Whyte, An Experiment in Autonomous Navigation of an Underground Mining Vehicle, IEEE Transactions on Robotics and Automation, Vol. 15, No. 1 ,pp. 85-95, 1999.
[11] K. Khoshelham and S. Oude Elberink, Accuracy and Resolution of Kinect Depth Data for Indoor Mapping Applications, Journal of MDPI Open Access Sensors, Vol. 12, No. 1 ,pp. 1437-1454, February, 2012.
[12] T. Fawcett, An Introduction to ROC analysis, Pattern Recognition Letters, Vol. 27, No. 1, pp. 861-874, December, 2005.
[13] S. Battiato and G.M. Farinella and G. Puglisi. SVG Vectorization by Statistical Region Merging. Proceedings of 4th Conference Eurographics Italian Chapter, pages 1-7, July, 2006.
[14] R. Nock and F. Nielsen, Statistical Region Merging, IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 26, No. 11 ,pp. 1-7, November, 2004.
[15] F. Calderero and F. Marques, Region Merging Techniques Using Information Theory Statistical Measures, IEEE Transactions on Image Processing, Vol. 19, No. 16 ,pp. 1567-1586, June, 2010.
[16] M.E. Celebi and H. A. Kingravi and J. Lee and W. Stoecker and J. M. Malters and H. Iyatomi and Y.A. Aslandogan and R. Moss and A.A. Marghoob, Fast and Accurate Border Detection in Dermoscopy Images Using Statistical Region Merging, TexasWorkforce Commission James A. Schlipmann Melanoma Cancer Foundation and NIH (SBIR 2R44 CA-101639-02A2), No. 16 ,pp. 1-10, 2006.
[17] H. Li and H. Gu and Y. Han and J. Yang, An Efficient Multiscale SRMMHR (Statistical Region Merging and Minimum Heterogeneity Rule) Segmentation Method for High Resolution Remote Sensing Imagery, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, Vol. 2, No. 2 ,pp. 67-73, June, 2009.
[18] Bretterk. Irominers, Available online: http://brettberk.com/wpcontent/ uploads/2009/05/death-valley-looking-inside-mine-shaft.jpg (accessed on 10 May 2012).
[19] C. Hsu and F. Lian and C. Huang and Y. Chang. Detecting Drivable Space in Traffic Scene Understanding. Proceedings of the IEEE International Conference on Systems Science and Engineering, pp 79-84, June, 2012.
[20] S. Zhou and J. Gong and G. Xiong and H. Chen and K. Iagnemma. Road Detection using Support Vector Machine Based on Online Learning and Evaluation. In IEEE Intelligent Vehicles Symposium, pp 256-262., San Diego USA, 2010.
[21] W. Jian and J. zhong and S. Yu-Ting. Unstructured Road Detection using Hybrid Features. Proceedings of the Eighth International Conference on Machine Learning and Cybernetics,, pp. 482-486., July 2009.
[22] S.R. Teleka and J. J. Green and S. Brink and J. Sheer and K. Hlophe. The Automation of the ÔÇÿMaking Safe- Process in South African Hard-Rock Underground Mines, International Journal of Engineering and Advanced Technology (IJEAT) Vol. 1, pp. 1-7., April 2012.